One Shot Generative

One-shot generative models aim to create new data instances from a single example, addressing the challenge of learning from limited data. Current research focuses on improving the efficiency and robustness of these models, particularly using diffusion models and generative adversarial networks (GANs), often incorporating techniques like variational autoencoders (VAEs) and transformers to enhance generation quality and control. These advancements have implications across diverse fields, including image processing, data augmentation for challenging tasks like UAV identification and medical imaging reconstruction, and improving the robustness of AI systems against adversarial attacks. The ability to generate realistic data from minimal input holds significant potential for various applications where data scarcity is a limiting factor.

Papers

August 31, 2024

LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion Models
Hossein Khalili, Seongbin Park, Vincent Li, Brandan Bright, Ali Payani, Ramana Rao Kompella, Nader Sehatbakhsh
Diffusion Model Adversarial Training Adversarial Robustness Mobile Device Adversarial Purification Adversarial Machine Learning One Shot Generative

August 30, 2024

Abstracted Gaussian Prototypes for One-Shot Concept Learning
Chelsea Zou, Kenneth J. Kurtz
Variational Autoencoders Concept Learning One Shot Generative

June 28, 2023

You Can Generate It Again: Data-to-text Generation with Verification and Correction Prompting
Xuan Ren, Lingqiao Liu
Faithful Generation Verification Task Language Correction Data to Text Generation Text Description Structured Input One Shot Generative

June 8, 2023

Complexity-aware Large Scale Origin-Destination Network Generation via Diffusion Model
Can Rong, Jingtao Ding, Zhicheng Liu, Yong Li
Diffusion Model Complexity Matter Network Analysis Network Structure Origin Destination One Shot Generative Urban Network

February 16, 2023

TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generation
Yunliang Jiang, Lili Yan, Xiongtao Zhang, Yong Liu, Danfeng Sun
Generative Adversarial Network Vision Transformer Image Generation C Gan One Shot Generative

January 20, 2023

One-shot Generative Data Augmentation with Bounded Divergence for UAV Identification in Limited RF Environments
Amir Kazemi, Salar Basiri, Volodymyr Kindratenko, Srinivasa Salapaka
Unmanned Aerial Vehicle Wireless Signal Norm Bounded One Shot Generative UAV Classification

August 15, 2022

One-shot Generative Prior in Hankel-k-space for Parallel Imaging Reconstruction
Hong Peng, Chen Jiang, Jing Cheng, Minghui Zhang, Shanshan Wang, Dong Liang, Qiegen Liu
Generative Model K Space Parallel Imaging Reconstruction One Shot Generative

May 20, 2022

Diversity vs. Recognizability: Human-like generalization in one-shot generative models
Victor Boutin, Lakshya Singhal, Xavier Thomas, Thomas Serre
Generative Model Diversity Awareness Human Like Generalization One Shot Generative

One Shot Generative

Papers

LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion Models

Abstracted Gaussian Prototypes for One-Shot Concept Learning

You Can Generate It Again: Data-to-text Generation with Verification and Correction Prompting

Complexity-aware Large Scale Origin-Destination Network Generation via Diffusion Model

TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generation

One-shot Generative Data Augmentation with Bounded Divergence for UAV Identification in Limited RF Environments

One-shot Generative Prior in Hankel-k-space for Parallel Imaging Reconstruction

Diversity vs. Recognizability: Human-like generalization in one-shot generative models